Analysis of machine learning algorithms for character recognition: a case study on handwritten digit recognition
Owais Mujtaba Khandy, Samad Dadvandipour
Abstract
<p><span>This paper covers the work done in handwritten digit recognition and the various classifiers that have been developed. Methods like MLP, SVM, Bayesian networks, and Random forests were discussed with their accuracy and are empirically evaluated. Boosted LetNet 4, an ensemble of various classifiers, has shown maximum efficiency among these methods. </span></p>
Topics & Concepts
Digit recognitionPattern recognition (psychology)Computer scienceArtificial intelligenceSpeech recognitionSupport vector machineCharacter (mathematics)Random forestCharacter recognitionIntelligent word recognitionBayesian probabilityNumerical digitBayesian networkMachine learningIntelligent character recognitionArtificial neural networkMathematicsArithmeticImage (mathematics)GeometryHandwritten Text Recognition TechniquesVehicle License Plate RecognitionText and Document Classification Technologies